fixed local entropy in best splits

src/DecisionTree.cpp

@@ -13,7 +13,7 @@ using namespace std;
 DecisionTree::DecisionTree(vector <vector<string>> data, int maxDepth, float featureWeight,
                            vector <FeatureType> featureType) {
 
-    // vector<int> index = randomSelect_WithoutReplacement(15, featureWeight);
+    // vector<int> index = randomSelect_WithoutReplacement(data.size(), featureWeight);
     // for(int i=0; i<index.size();i++){
     //     for(int j=1; j<data[index[i]].size(); j++){
     //         data[index[i]][j] = data[index[i]][0];
@@ -68,6 +68,7 @@ Node *train(vector <vector<string>> data, vector <FeatureType> featureType,
         BestSplitPoint bestSplit = findBestSplit(parentEntropy, currentDepth, potentialSplits, data,
                                                  featureType);
 
+        //cout << "------ best split index "<<bestSplit.featureIdx<<endl;
         if(bestSplit.featureIdx == -1){
             Node *leaf = new Node(NULL, NULL, NULL, true, classification, originalEntropy, informationGainFromParent);
 //            cout<<"No more split"<<endl;
@@ -171,7 +172,7 @@ string DecisionTree::predictSingle(vector <string> test, Node *treeRoot) {
             answer = treeRoot->falseBranch;
         }
     } else {
-        if (test[splitIndex] >= splitValue) {
+        if ( stod(test[splitIndex]) >= stod(splitValue)) {
             answer = treeRoot->trueBranch;
         } else {
             answer = treeRoot->falseBranch;

src/RandomForest.cpp

@@ -245,7 +245,6 @@ accuracyReport RandomForest::getAccuracy(vector<vector<string>> testData){
     }
 
     accuracyReport report = {accuracy,correctLables,incorrectLables,correct,incorrect,total};
-    cout << "here"<< endl;
     return report;
     
 

src/helpers.cpp

@@ -202,6 +202,9 @@ float calculateEntropy(vector <vector<string>> data) {
             entropy -= (probability) * log2(probability);
         }
     }
+    if(entropy == 1){
+        //cout << "size with one entropy "<< dataCount.size()<<endl;
+    }
     return entropy;
 }
 
@@ -215,7 +218,8 @@ float calculateSplitEntropy(FeatureSplitData featsplitData) {
 
     float splitEntropy = (probabilityDataTrue * calculateEntropy(splitDataTrue)) +
                          (probabilityDataFalse * calculateEntropy(splitDataFalse));
-
+    
+    //cout << "Split Entropy "<<splitEntropy<<endl;
     return splitEntropy;
 
 }
@@ -251,7 +255,7 @@ splitData(vector <vector<string>> data, int splitFeature, vector <FeatureType> f
         }
     } else {
         for (int dataIdx = 0; dataIdx < splitFeatureData.size(); dataIdx++) {
-            if (splitFeatureData[dataIdx] >= splitValue) {
+            if (stod(splitFeatureData[dataIdx]) >= stod(splitValue)) {
                 for (int featureIdx = 0; featureIdx < data.size(); featureIdx++) {
                     splitTrue.at(featureIdx).push_back(data.at(featureIdx).at(dataIdx));
                 }
@@ -276,28 +280,48 @@ BestSplitPoint findBestSplit(double parentEntropy, int currentDepth,std::map<int
     float entropy = 9999;
     int bestSplitFeature;
     string bestSplitValue;
+    bool first_iteration = true;
 
     map < int, set < string >> ::iterator
     itr;
     for (itr = potentialSplits.begin(); itr != potentialSplits.end(); ++itr) {
-        //cout << itr->first << " " << itr->second.size() << endl;
-        float localEntropy = 1;
+        if (itr->second.size() == 0){
+            cout << itr->first << " " << itr->second.size() << endl;
+            cout << "feature types "<<featureTypes[itr->first]<<endl;
+        }
+        float localEntropy;
+        bool firstsplit = true;; 
         set <string> splits = itr->second;
         if (splits.size() > 0) {
+  
             set<string>::iterator splitItr;
             for (splitItr = splits.begin(); splitItr != splits.end(); splitItr++) {
-//                cout<<"Spliting "<<endl;
                 FeatureSplitData featSplitData = splitData(data, itr->first, featureTypes, (*splitItr));
 
                 float splitEntropy = calculateSplitEntropy(featSplitData);
                 if (featureTypes[itr->first] ==CONTINUOUS) {
-                    if (localEntropy > splitEntropy) {
+                    if(firstsplit){
+                        firstsplit = false;
                         localEntropy = splitEntropy;
-                    } else {
-                        break;
                     }
+                    else{
+                        if (localEntropy > splitEntropy) {
+                            localEntropy = splitEntropy;
+                            
+                            if(splitEntropy ==1){
+                                //cout << "It is one \n";
+                            }
+                        }
+                        else
+                        { 
+                            break;
+                        }
+                    }
+                    
+                    
                 }
-                if (splitEntropy <= entropy) {
+                if (first_iteration || splitEntropy <= entropy) {
+                    first_iteration = false;
                     entropy = splitEntropy;
 //                cout<<itr->first<<" ";
                     bestSplitFeature = itr->first;
@@ -310,9 +334,21 @@ BestSplitPoint findBestSplit(double parentEntropy, int currentDepth,std::map<int
         }
     }
 
+    
+    //cout <<"!!!!!!!!!! "<< bestSplitValue << endl;
+
     if(currentDepth!=0 && parentEntropy<entropy){
-        BestSplitPoint splitPoint = {-1, ""};
-        return splitPoint; 
+        bestSplitFeature = -1;
+        bestSplitValue = "";
+    }
+
+    if(bestSplitFeature>15 || bestSplitFeature <-1){
+         map < int, set < string >> ::iterator
+        itr;
+        for (itr = potentialSplits.begin(); itr != potentialSplits.end(); ++itr) {
+            cout << "------------- "<<endl;
+            cout << itr->first << " " << itr->second.size() << endl;
+        }
     }
 
     BestSplitPoint splitPoint = {bestSplitFeature, bestSplitValue};
@@ -414,6 +450,11 @@ findAllSplittingPoints(vector <vector<string>> data, vector <FeatureType> featur
     set <string> temp;
 
     vector<int> index = randomSelect_WithoutReplacement(data.size(), featureWeight);
+    // vector<int> index (data.size());
+    // for ( int j = 0; j< data.size(); j++){
+    //     index[j] = j; 
+    // }
+
     for (int i = 0; i < index.size(); i++) {
         temp.clear();
         if (index[i] != data.size() - 1) { //because the last entry is the label
@@ -428,11 +469,13 @@ findAllSplittingPoints(vector <vector<string>> data, vector <FeatureType> featur
                 vector <string> continuousData = data[index[i]];
                 sort(continuousData.begin(), continuousData.end());
                 //Unsupervised binning for continuous data
-                int K = 20;
-                if((continuousData[continuousData.size() - 1]) == continuousData[0]){
+                int K = 100;
+                if(stod(continuousData[continuousData.size() - 1]) == stod(continuousData[0])){
                     continue;
                 }
-                double w = (stod(continuousData[continuousData.size() - 1]) - stod(continuousData[0])) / K;
+                else
+                {
+                   double w = (stod(continuousData[continuousData.size() - 1]) - stod(continuousData[0])) / K;
 
 
                 if (w) {
@@ -453,8 +496,16 @@ findAllSplittingPoints(vector <vector<string>> data, vector <FeatureType> featur
 //                    temp.insert(continuousData[j]);
 
 //                }
+             
 
                 possibleSplits[index[i]] = temp;
+                if(temp.size() == 0){
+                    cout<< "Size is zerooooo"<<endl;
+                }
+                }
+                
+
+                
 
 //                cout<<temp.size()<<" of feature Continuous "<< index[i]<<endl;
 

src/test.cpp

@@ -35,7 +35,7 @@ int main(int argc, char *argv[]) {
     int numTrees = atoi(argv[1]);
     float depth = atoi(argv[2]);
     float baggingWeight = 0.7;
-    float featWeight = 0.7;
+    float featWeight = 0.3;
     //float baggingWeight = atoi(argv[2]) * 0.1;
     // double featWeight = numFeatures * 0.1;
 
@@ -45,9 +45,9 @@ int main(int argc, char *argv[]) {
     vector <vector<string>> datasetAsString;
     vector <FeatureType> featureTypes;
     vector <string> features;
-    datasetAsString = parseDataToString("../datasets/adult.data");
-    featureTypes = parseFeatureTypes("../datasets/adult.featureTypes");
-    features = parseFeatures("../datasets/adult.features");
+    datasetAsString = parseDataToString("../datasets/loan.data");
+    featureTypes = parseFeatureTypes("../datasets/loan.featureTypes");
+    features = parseFeatures("../datasets/loan.features");
 
 
     double accuracy = 0.0;

src/test.sh

@@ -2,10 +2,8 @@
 for i in {5..100..5}
 do 
 #    ./race $i 10
-     for j in {5..10}
+     for j in {5..7}
      do
          ./race $i $j
-         ./race $i $j
-         ./race $i $j
      done
 done
\ No newline at end of file